Hi Luis,<br><br>Thank you. I'll try this and let you know of my progress.<br><br>thanks,<br>John<br><br><div class="gmail_quote">On Tue, Apr 27, 2010 at 11:58 PM, Luis Ibanez <span dir="ltr"><<a href="mailto:luis.ibanez@kitware.com">luis.ibanez@kitware.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><br>Hi John,<br><br>If you are looking for a way of characterizing the <br>registration method itself, then you may want to<br>
consider doing the following:<br><br>1) Take an image representative of your domain.<br><br>2) Apply to it a known deformation<br>
<br>3) Use the image (1) as moving image and the <br> image (2) as fixed image<br><br>4) Compare the deformation field resulting from<br> the registration (3) with the known field that<br> you used in (2). The differences between the<br>
fields will give you an idea of the accuracy <br> of the registration.<br><br>For step (2), you may find useful the examples<br><br> Insight/Examples/Registration/<br> BSplineWarping1.cxx<br>
BSplineWarping2.cxx<br> LandmarkWarping2.cxx<br> ThinPlateSplineWarp.cxx<br> <br><br>Please be very careful of avoiding generalizations.<br>
Registration results are very dependent on the setting <br>of parameters. Whatever measure of accuracy you<br>obtain, will only be representative of that registration<br>method WITH those exact parameters. <br><br>You should therefore, repeat the entire process for <br>
a variety of parameters, and report on all the sequence.<br><br>It is a common mistake to report registration results<br>by just using a setting of parameters. This is mostly <br>seen in conferences and journals that do not enforce<br>
or encourage reproducibility (sadly most of them).<br><br><br> Regards,<br><br><br> Luis<br><br><br>----------------------------------------------------------------------<br><div class="gmail_quote"><div>
<div></div><div class="h5">On Mon, Apr 26, 2010 at 6:30 PM, John Jan Drozd <span dir="ltr"><<a href="mailto:john.drozd@gmail.com" target="_blank">john.drozd@gmail.com</a>></span> wrote:<br>
</div></div><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><div><div></div><div class="h5">Hi,<br>
<br>
Is there a way to quantify the accuracy of a deformable registration? I used the diffeomorphic demons deformable registration.<br>
<br>
Thank you,<br>
John<br>
<br>
Sent from my iPhone<br></div></div><div class="im">
_____________________________________<br>
Powered by <a href="http://www.kitware.com" target="_blank">www.kitware.com</a><br>
<br>
Visit other Kitware open-source projects at<br>
<a href="http://www.kitware.com/opensource/opensource.html" target="_blank">http://www.kitware.com/opensource/opensource.html</a><br>
<br>
Kitware offers ITK Training Courses, for more information visit:<br>
<a href="http://www.kitware.com/products/protraining.html" target="_blank">http://www.kitware.com/products/protraining.html</a><br>
<br>
Please keep messages on-topic and check the ITK FAQ at:<br>
<a href="http://www.itk.org/Wiki/ITK_FAQ" target="_blank">http://www.itk.org/Wiki/ITK_FAQ</a><br>
<br>
Follow this link to subscribe/unsubscribe:<br>
<a href="http://www.itk.org/mailman/listinfo/insight-users" target="_blank">http://www.itk.org/mailman/listinfo/insight-users</a><br>
</div></blockquote></div><br>
</blockquote></div><br>